Simple Regression

In [1]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
import warnings
warnings.filterwarnings('ignore')
%config InlineBackend.figure_format = 'retina'

In [2]:

data = pd.read_csv("Salary_Data.csv")

In [3]:

data

Out[3]:

	YearsExperience	Salary
0	1.1	39343.0
1	1.3	46205.0
2	1.5	37731.0
3	2.0	43525.0
4	2.2	39891.0
5	2.9	56642.0
6	3.0	60150.0
7	3.2	54445.0
8	3.2	64445.0
9	3.7	57189.0
10	3.9	63218.0
11	4.0	55794.0
12	4.0	56957.0
13	4.1	57081.0
14	4.5	61111.0
15	4.9	67938.0
16	5.1	66029.0
17	5.3	83088.0
18	5.9	81363.0
19	6.0	93940.0
20	6.8	91738.0
21	7.1	98273.0
22	7.9	101302.0
23	8.2	113812.0
24	8.7	109431.0
25	9.0	105582.0
26	9.5	116969.0
27	9.6	112635.0
28	10.3	122391.0
29	10.5	121872.0

In [6]:

# see the pre-defined styles provided.
plt.style.available

Out[6]:

['seaborn-bright',
 'classic',
 'seaborn-colorblind',
 'grayscale',
 'seaborn-talk',
 'seaborn-muted',
 'ggplot',
 'bmh',
 'seaborn-whitegrid',
 'seaborn-paper',
 'seaborn-white',
 'seaborn-dark-palette',
 'fivethirtyeight',
 'dark_background',
 'seaborn-dark',
 'seaborn-darkgrid',
 'seaborn',
 'seaborn-deep',
 'seaborn-poster',
 'seaborn-pastel',
 'seaborn-ticks',
 'seaborn-notebook']

In [7]:

# use the 'seaborn-colorblind' style
plt.style.use('fivethirtyeight')

In [8]:

plt.scatter(data.YearsExperience, data.Salary)

Out[8]:

<matplotlib.collections.PathCollection at 0x1132565f8>

In [12]:

sns.lmplot(x = "YearsExperience", y = "Salary", data = data, size = 7)

Out[12]:

<seaborn.axisgrid.FacetGrid at 0x1138ae3c8>

In [36]:

X

Out[36]:

0      1.1
1      1.3
2      1.5
3      2.0
4      2.2
5      2.9
6      3.0
7      3.2
8      3.2
9      3.7
10     3.9
11     4.0
12     4.0
13     4.1
14     4.5
15     4.9
16     5.1
17     5.3
18     5.9
19     6.0
20     6.8
21     7.1
22     7.9
23     8.2
24     8.7
25     9.0
26     9.5
27     9.6
28    10.3
29    10.5
Name: YearsExperience, dtype: float64

In [37]:

X = data.iloc[:,0].values

In [38]:

y = data.iloc[:,1].values

In [39]:

from sklearn.model_selection import train_test_split

In [52]:

X_train,X_test, y_train, y_test = train_test_split(X,y, test_size = 1/3, random_state = 0)

Linear Regression¶

In [53]:

from sklearn.linear_model import LinearRegression

In [54]:

model = LinearRegression()

In [55]:

model.fit(X_train.reshape(-1,1),y_train)

Out[55]:

LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)

In [56]:

y_pred = model.predict(X_test.reshape(-1,1))

In [57]:

y_pred

Out[57]:

array([  40835.10590871,  123079.39940819,   65134.55626083,
         63265.36777221,  115602.64545369,  108125.8914992 ,
        116537.23969801,   64199.96201652,   76349.68719258,
        100649.1375447 ])

In [58]:

y_test

Out[58]:

array([  37731.,  122391.,   57081.,   63218.,  116969.,  109431.,
        112635.,   55794.,   83088.,  101302.])

In [68]:

plt.figure(figsize=(10,8))
sns.regplot(X_train,y_train, label="Train set")
plt.scatter(X_test,y_test, c="orange", label = "Test set")
plt.legend()

Out[68]:

<matplotlib.legend.Legend at 0x10f7537f0>

In [ ]: